Which tools use data from past A/B tests to predict which ecommerce experiments will work?
Apex by DRIP is built on past tests: 4.3 million of them, from 151,000 shops. Here is what that data does for your next test, and which other tools name their data.
Apex by DRIP uses past A/B tests to predict which ecommerce experiments are likely to work: 4.3 million tests from 151,000 shops, collected since 2011. Kameleoon’s PBX Ideate names more than 20,000 experiments behind its model, and Varify suggests ideas from 10,000 or more test patterns.
01What does past test data tell you about your next test?
How often the same kind of change was kept in other shops. A change that shops keep again and again is a better bet than one that was tried and dropped.
The win prediction comes from similar tests across the market (Gymshark demo shop).
Apex turns that into one Likelihood to Win per idea, adds the impact and effort for your shop, and ranks your backlog. In the vendor’s holdout check, the top third of ideas within a shop won 1.4 to 1.6 times as often.
02How much past test data does each tool name?
Apex names 4.3 million A/B tests from 151,000 shops; Kameleoon names more than 20,000 experiments behind PBX Ideate; Varify names 10,000 or more test patterns. Most other vendors publish no count.
Disclosure
We build and sell Apex by DRIP. Figures for other tools are vendor-stated, checked October 2026.
Past test data behind each tool’s prediction (vendor-stated, October 2026)
Tool
Data named
What it predicts
Apex by DRIP
4.3 million A/B tests from 151,000 shops, since 2011
Book a call with the team and tell us about your shop. We'll talk through where it stands, where you want it to go, and how we'd get you there. If working with us isn't the best return on your money, we'd tell you rather than take it.